Leading AI practices. Agentic network engineering https://nitter.cf/t.co/j0Gu0Qq4RZ Systems not the prompts https://nitter.cf/t.co/a2Ram1Rarv
MD
Joined November 2015
- Tweets7.4K
- Following792
- Followers1.4K
- Likes3.4K
Donte retweeted
Decision Desk HQ projects James Talarico wins the TX US Senate General Election
#DecisionMade: 10:14 PM EST
Follow live results here: votes.decisiondeskhq.com/rac…
Donte retweeted
Decision Desk HQ projects Jon Ossoff wins the GA US Senate General Election
#DecisionMade: 7:18 PM EST
Follow live results here: votes.decisiondeskhq.com/rac…
4. When I use Fable: rarely, and only by name.
When I'm stuck on a problem that i can solve i use fable and break it down into as close a principle i can and use that to build on.
5. Minimizing usage: structure, not willpower.
A knowledge bank: findings get IDs, and agents cite IDs instead of re-researching.
Narrow briefs: a sub-agent gets the files to read, the goal and what’s ruled out. It returns a 15-line summary, not file dumps.
Small batches (at most 10 things for human review) and automated gates before any human time.
Hooks warn on untyped agents and heavy jobs started by day, and block writes to protected data.
Measure it: log tokens per model per session, and re-check spend on a date.
3. Model selection: the cheapest tier that can judge.
Mechanical (run, count, move, queue, read a summary): the small model (Haiku).
Judgment against sources (research, analysis, writing, review of data): the mid model (Sonnet).
Design, hard code, adversarial and security review: the top model (Opus).
Minimize sub agents as much as possible and dont use general agents as they default to the parent so you could be using opus for task that needs hakiu
It would take me about 30 min to explain, but short answer is.
Workflow: one conductor, one queue.
One main session owns the plan and a live work queue. Each row has an owner, a status, and “superseded by”.
Before starting anything, check whether newer work made it moot. Most wasted spend is work that was already dead. Rabbit holes get parked as “deep dive later”, not chased. Finish first, iterate later.
2. What goes on the queue: anything long, heavy or repeatable.
If it runs over a few minutes, hogs a resource (GPU, CPU, network, a drive), or repeats nightly, it’s a queued job: a plain command with a resource class, a resume key and a time window. It isn’t an agent.
Prove one item in the foreground (--limit 1, --dry-run); queue the batch. Agents decide what to run; code runs it. Never pay a model to babysit a loop.
Single agent loops will be the thing in 2027 in frontier models. If you are still doing multi agent for new projects you are behind the curve